Jun Ma
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Jun Ma has a total of 56 co-authors. Here are the top co-authors by number of shared publications:
- Shasha Li
National university of defense technology, Changsha, China
7 shared publications - Bin Ji
National university of defense technology, Changsha, China
5 shared publications - Jie Yu
National university of defense technology, Changsha, China
5 shared publications - Huijun Liu
National University of Defense Technology
4 shared publications - Jie Yu
College of Computer, National University of Defense Technology, Changsha, China
4 shared publications - Jing Wang
National university of defense technology, Changsha, China
4 shared publications
Latest Publications
- Open Access
- 9 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 12010-12019
Beyond Token Stacking: Multi-scale Visual Modulation and Adaptive Fused-feature Calibration for MLLMs
- 9 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 12010-12019
Open AccessBeyond Token Stacking: Multi-scale Visual Modulation and Adaptive Fused-feature Calibration for MLLMs
- 6 November 2026
- Published by Springer Nature
- p. 64-78
Axiomatic Risk Propagation with Temporal Dynamics: Identifying High-Risk Packages in Software Supply Chains
- 6 November 2026
- Published by Springer Nature
- p. 64-78
Axiomatic Risk Propagation with Temporal Dynamics: Identifying High-Risk Packages in Software Supply Chains
- Open Access
- 1 October 2026
- Published by Association for Computing Machinery (ACM) in Proceedings of the ACM on Software Engineering
- Vol. 3 (ISSTA) , 2338-2360
Just Old Wine in a New Bottle: Improving Vulnerability Repair Robustness to Combat Homologous but Heterogeneous Vulnerabilities
Collaborative development practices, such as forking and branching, enable parallel development and rapid iteration but significantly complicate vulnerability management. A major challenge is the propagation of homologous but heterogeneous vulnerabilities, where the same vulnerability appears within evolved code contexts that differ structurally and contextually across divergent branches or forks.Existing Automated Vulnerability Repair (AVR) approaches often fail in these scenarios due to their limited ability to generalize across structural and contextual variations. To address this problem, we propose EvoRepair, a robust AVR framework tailored for code evolution contexts. Our approach leverages a Retrieval-Augmented Generation based Evolution Specialist to synthesize code evolution variants, enriching the training data with diverse code contexts. We then employ Chain-of-Thought reasoning and curriculum learning to train a Repair Specialist, enabling it to capture invariant repair logic during structural and contextual changes. We evaluate EvoRepair on two datasets representing cross-branch and cross-fork scenarios. Evaluation results demonstrate that EvoRepair successfully repaired 35.33% of the vulnerabilities on average in evolution scenarios, outperforming the state-of-the-art baseline Vul-R2 by 42.12%. Furthermore, EvoRepair also demonstrates superior generalizability in non-evolution scenarios, achieving state-of-the-art performance on the PrimeVul dataset by fixing 25.75% of the vulnerabilities, surpassing the best baseline by 21.75%.
- 1 October 2026
- Published by Association for Computing Machinery (ACM) in Proceedings of the ACM on Software Engineering
- Vol. 3 (ISSTA) , 2338-2360
Open AccessJust Old Wine in a New Bottle: Improving Vulnerability Repair Robustness to Combat Homologous but Heterogeneous Vulnerabilities
Collaborative development practices, such as forking and branching, enable parallel development and rapid iteration but significantly complicate vulnerability management. A major challenge is the propagation of homologous but heterogeneous vulnerabilities, where the same vulnerability appears within evolved code contexts that differ structurally and contextually across divergent branches or forks.Existing Automated Vulnerability Repair (AVR) approaches often fail in these scenarios due to their limited ability to generalize across structural and contextual variations. To address this problem, we propose EvoRepair, a robust AVR framework tailored for code evolution contexts. Our approach leverages a Retrieval-Augmented Generation based Evolution Specialist to synthesize code evolution variants, enriching the training data with diverse code contexts. We then employ Chain-of-Thought reasoning and curriculum learning to train a Repair Specialist, enabling it to capture invariant repair logic during structural and contextual changes. We evaluate EvoRepair on two datasets representing cross-branch and cross-fork scenarios. Evaluation results demonstrate that EvoRepair successfully repaired 35.33% of the vulnerabilities on average in evolution scenarios, outperforming the state-of-the-art baseline Vul-R2 by 42.12%. Furthermore, EvoRepair also demonstrates superior generalizability in non-evolution scenarios, achieving state-of-the-art performance on the PrimeVul dataset by fixing 25.75% of the vulnerabilities, surpassing the best baseline by 21.75%.
- Open Access
- 30 June 2026
- Published by Association for Computing Machinery (ACM) in Proceedings of the ACM on Software Engineering
- Vol. 3 (FSE) , 4323-4346
Three Heads Are Better Than One: A Multi-perspective Reasoning Framework for Enhanced Vulnerability Detection
Automated vulnerability detection is crucial for enhancing software security by identifying potential flaws that attackers could exploit, thereby reducing the reliance on labor-intensive manual code audits. Recent advancements have shifted towards leveraging large language models (LLMs) for vulnerability detection, with techniques like Vul-RAG and VulnSage demonstrating progress through structured prompting and external knowledge integration. However, these approaches typically rely on a single reasoning paradigm, limiting their ability to address the complex and diverse nature of real-world vulnerabilities. To overcome these limitations, we propose ReasonVul, a novel multi-perspective reasoning framework that harnesses cognitive synergy among three specialized LLM agents, each embodying a distinct reasoning mode. The framework begins with independent analyses of the source code, followed by a structured debate mechanism to resolve conflicts through iterative rebuttal and revision, ultimately converging on a collaborative judgment. Evaluated on the PrimeVul dataset, ReasonVul achieves a PairAcc of 40.00% and an F1-score of 72.52%, surpassing the best baseline by 81.24% in PairAcc. Further tests on the JITVUL dataset confirm its generalizability, with a PairAcc of 28.67%. Additionally, we analyzed 542 conflict cases and found that 389 were correctly resolved, highlighting the framework's ability to uncover hidden vulnerabilities through the error-correction mechanism driven by the debate. This work emphasizes the importance of multi-perspective reasoning and collaborative validation in achieving robust and comprehensive vulnerability detection in real-world software systems.
- 30 June 2026
- Published by Association for Computing Machinery (ACM) in Proceedings of the ACM on Software Engineering
- Vol. 3 (FSE) , 4323-4346
Open AccessThree Heads Are Better Than One: A Multi-perspective Reasoning Framework for Enhanced Vulnerability Detection
Automated vulnerability detection is crucial for enhancing software security by identifying potential flaws that attackers could exploit, thereby reducing the reliance on labor-intensive manual code audits. Recent advancements have shifted towards leveraging large language models (LLMs) for vulnerability detection, with techniques like Vul-RAG and VulnSage demonstrating progress through structured prompting and external knowledge integration. However, these approaches typically rely on a single reasoning paradigm, limiting their ability to address the complex and diverse nature of real-world vulnerabilities. To overcome these limitations, we propose ReasonVul, a novel multi-perspective reasoning framework that harnesses cognitive synergy among three specialized LLM agents, each embodying a distinct reasoning mode. The framework begins with independent analyses of the source code, followed by a structured debate mechanism to resolve conflicts through iterative rebuttal and revision, ultimately converging on a collaborative judgment. Evaluated on the PrimeVul dataset, ReasonVul achieves a PairAcc of 40.00% and an F1-score of 72.52%, surpassing the best baseline by 81.24% in PairAcc. Further tests on the JITVUL dataset confirm its generalizability, with a PairAcc of 28.67%. Additionally, we analyzed 542 conflict cases and found that 389 were correctly resolved, highlighting the framework's ability to uncover hidden vulnerabilities through the error-correction mechanism driven by the debate. This work emphasizes the importance of multi-perspective reasoning and collaborative validation in achieving robust and comprehensive vulnerability detection in real-world software systems.
- Open Access
- 12 April 2026
- Published by Association for Computing Machinery (ACM)
- p. 3847-3858
EMSEdit: Efficient Multi-Step Meta-Learning-based Model Editing
- 12 April 2026
- Published by Association for Computing Machinery (ACM)
- p. 3847-3858
Open AccessEMSEdit: Efficient Multi-Step Meta-Learning-based Model Editing
- Open Access
- 16 December 2025
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Architecture and Code Optimization
- Vol. 22 (4) , 1-26
HotLD: A Workload-Aware Method for Global Code-Layout Optimization of Shared Libraries
Dynamic linking is an important technique in the process of software development. While dynamic linking can save memory and enhance maintainability, it also incurs performance overhead and hinders the application of profile-guided code layout optimization techniques to third-party libraries. Existing works (such as BOLT) can solve the problem by generating optimized versions of shared libraries for a given workload. Online PGO methods (such as OCOLOS) can further support on-the-fly code replacement to adapt to workload changes. These methods, however, are limited in several aspects: (1) hard to perform global optimization, (2) high memory consumption and performance overhead, and (3) limited usage scenarios. To address these issues, we propose HotLD , a workload-aware method for global code-layout optimization of shared libraries. HotLD can improve the performance of shared libraries while introducing limited performance and memory overhead. The core idea behind HotLD is to create dedicated code copies for each typical application workload during the offline phase, and perform global optimization according to workload characteristics. At runtime, HotLD monitors the running workload of the target program, then dynamically selects and links an appropriate code copy. We conducted experiments using real-world applications to evaluate the effectiveness and efficiency of HotLD . The results demonstrate that HotLD can improve their performance (up to 22.37%) with limited performance overhead (at the millisecond level). Compared with existing works, HotLD uses 1%–46% memory to support 2×–9× workloads.
- 16 December 2025
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Architecture and Code Optimization
- Vol. 22 (4) , 1-26
Open AccessHotLD: A Workload-Aware Method for Global Code-Layout Optimization of Shared Libraries
Dynamic linking is an important technique in the process of software development. While dynamic linking can save memory and enhance maintainability, it also incurs performance overhead and hinders the application of profile-guided code layout optimization techniques to third-party libraries. Existing works (such as BOLT) can solve the problem by generating optimized versions of shared libraries for a given workload. Online PGO methods (such as OCOLOS) can further support on-the-fly code replacement to adapt to workload changes. These methods, however, are limited in several aspects: (1) hard to perform global optimization, (2) high memory consumption and performance overhead, and (3) limited usage scenarios. To address these issues, we propose HotLD , a workload-aware method for global code-layout optimization of shared libraries. HotLD can improve the performance of shared libraries while introducing limited performance and memory overhead. The core idea behind HotLD is to create dedicated code copies for each typical application workload during the offline phase, and perform global optimization according to workload characteristics. At runtime, HotLD monitors the running workload of the target program, then dynamically selects and links an appropriate code copy. We conducted experiments using real-world applications to evaluate the effectiveness and efficiency of HotLD . The results demonstrate that HotLD can improve their performance (up to 22.37%) with limited performance overhead (at the millisecond level). Compared with existing works, HotLD uses 1%–46% memory to support 2×–9× workloads.
- 12 December 2025
- Published by Elsevier in Information Processing & Management
- Vol. 63 (3)
SEAttack: A self-evolving jailbreak attack to induce toxic responses for non-toxic queries in large language models
- 12 December 2025
- Published by Elsevier in Information Processing & Management
- Vol. 63 (3)
SEAttack: A self-evolving jailbreak attack to induce toxic responses for non-toxic queries in large language models
- Open Access
- 3 August 2025
- Published by Association for Computing Machinery (ACM)
- p. 1553-1564
Identifying Knowledge Editing Types in Large Language Models
- 3 August 2025
- Published by Association for Computing Machinery (ACM)
- p. 1553-1564
Open AccessIdentifying Knowledge Editing Types in Large Language Models
- Open Access
- 27 October 2024
- Published by Association for Computing Machinery (ACM)
- p. 694-705
How to Pet a Two-Headed Snake? Solving Cross-Repository Compatibility Issues with Hera
Many programming languages and operating system communities maintain software repositories to build their own ecosystems. The repositories often provide management tools to help users using the packages. The tools are often, if not all the times, well-designed to handle intra-repository dependencies without considering inter-repository dependencies. The users, however, often need packages from different repositories, and thus may suffer from compatibility issues. We refer to these issues as Cross-repository Compatibility (CC) issues. Existing works typically focus on a single software repository and are insufficient to detect CC issues. To fill this gap, we use both Python and Ubuntu repositories as representatives to study the root cause of CC issues, then summarize their triggering patterns and failure symptoms. Guided by the above analysis, we design Hera, an automatic tool to solve CC issues. Hera first builds a cross-repository compatibility database offline, and then online predicts, detects and fixes CC issues in the user's system environment. In our evaluation, we construct a dataset of 1,692 real-world CC issues, and Hera can detect 3,689 issues with the precision of 90.5% and the recall of 93.7%. We also collected 27 real-world CC issues from GitHub and Stack Overflow, and reproduced 26 of them. Hera can detect all the 26 cases, and provide accurate reasons as well as fixing advice.
- 27 October 2024
- Published by Association for Computing Machinery (ACM)
- p. 694-705
Open AccessHow to Pet a Two-Headed Snake? Solving Cross-Repository Compatibility Issues with Hera
Many programming languages and operating system communities maintain software repositories to build their own ecosystems. The repositories often provide management tools to help users using the packages. The tools are often, if not all the times, well-designed to handle intra-repository dependencies without considering inter-repository dependencies. The users, however, often need packages from different repositories, and thus may suffer from compatibility issues. We refer to these issues as Cross-repository Compatibility (CC) issues. Existing works typically focus on a single software repository and are insufficient to detect CC issues. To fill this gap, we use both Python and Ubuntu repositories as representatives to study the root cause of CC issues, then summarize their triggering patterns and failure symptoms. Guided by the above analysis, we design Hera, an automatic tool to solve CC issues. Hera first builds a cross-repository compatibility database offline, and then online predicts, detects and fixes CC issues in the user's system environment. In our evaluation, we construct a dataset of 1,692 real-world CC issues, and Hera can detect 3,689 issues with the precision of 90.5% and the recall of 93.7%. We also collected 27 real-world CC issues from GitHub and Stack Overflow, and reproduced 26 of them. Hera can detect all the 26 cases, and provide accurate reasons as well as fixing advice.
- 8 July 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Knowledge and Data Engineering
- Vol. 37 (10) , 6246-6258
Win-Win Cooperation: Bundling Sequence and Span Models for Named Entity Recognition
For Named Entity Recognition (NER), sequence labeling-based and span-based paradigms are quite different. Previous studies have demonstrated the clear complementary advantages of the two paradigms, but few models have tried to incorporate them into a single NER model as far as we know. In our previous work, we proposed a paradigm called Bundling Learning (BL) to explore the above issue, which bundles the two NER paradigms, enabling NER models to jointly tune their parameters by weighted summing each paradigm's training loss. However, three critical issues remain unresolved: When does BL work? Why does BL work? Can BL enhance existing state-of-the-art NER models? To address the first two issues, we design three NER models: a sequence labeling-based model – SeqNER, a span-based NER model – SpanNER, and BL-NER which bundles SeqNER and SpanNER. We draw two conclusions regarding the two issues based on the experimental results on eleven NER datasets. To investigate the third issue, we apply BL to five existing state-of-the-art NER models, including three sequence labeling-based and two span-based models. Experimental results indicate consistent NER performance gains, suggesting a feasible way to construct new state-of-the-art NER systems by applying BL to the current state-of-the-art systems. Moreover, investigation results show that BL reduces both entity boundary and type prediction errors. In addition, we compare two commonly used label tagging methods and three types of span semantic representations.
- 8 July 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Knowledge and Data Engineering
- Vol. 37 (10) , 6246-6258
Win-Win Cooperation: Bundling Sequence and Span Models for Named Entity Recognition
For Named Entity Recognition (NER), sequence labeling-based and span-based paradigms are quite different. Previous studies have demonstrated the clear complementary advantages of the two paradigms, but few models have tried to incorporate them into a single NER model as far as we know. In our previous work, we proposed a paradigm called Bundling Learning (BL) to explore the above issue, which bundles the two NER paradigms, enabling NER models to jointly tune their parameters by weighted summing each paradigm's training loss. However, three critical issues remain unresolved: When does BL work? Why does BL work? Can BL enhance existing state-of-the-art NER models? To address the first two issues, we design three NER models: a sequence labeling-based model – SeqNER, a span-based NER model – SpanNER, and BL-NER which bundles SeqNER and SpanNER. We draw two conclusions regarding the two issues based on the experimental results on eleven NER datasets. To investigate the third issue, we apply BL to five existing state-of-the-art NER models, including three sequence labeling-based and two span-based models. Experimental results indicate consistent NER performance gains, suggesting a feasible way to construct new state-of-the-art NER systems by applying BL to the current state-of-the-art systems. Moreover, investigation results show that BL reduces both entity boundary and type prediction errors. In addition, we compare two commonly used label tagging methods and three types of span semantic representations.